Fermer
_fse_istat_choix.jpg

Small area estimation course

 

SMALL AREA ESTIMATION WITH EXAMPLES IN R

INSTRUCTOR: Isabel Molina, Universidad Carlos III de Madrid

DATES : October 18-19, 2012

PLACE :  University of Neuchâtel, av. 1er Mars 26, D71 (2nd floor)

ABSTRACT : Demand for timely and reliable small area estimates derived from survey data has increased greatly in recent years due to, among other things, their growing use in formulating policies and programs, allocation of government funds, regional planning, small area business decisions and other applications. Traditional area-specific (direct) estimates may not provide acceptable precision for small areas because sample sizes in small areas are seldom large enough or even zero sample sizes in many small areas of interest. This makes it necessary to borrow information across related areas through indirect estimation based on implicit or explicit linking models, using auxiliary information such as recent census data and current administrative data. Methods based on explicit linking models are now widely accepted. This workshop will provide an introduction to small area estimation, with a variety of applications to socio-economic data and practical demonstration of the methods in R statistical software.

TARGET AUDIENCE: The course is primary aimed at methodologists in government statistical bureaus or survey organizations, statistics graduate students and faculty from universities and users with adequate background in linear regression models and survey sampling theory and methods.

____________________________________________________________________________________________________

Course fee : CHF 400 (2 lunches inclueded).
 
Registration :   By e-mail before Friday 12 of October 2012  at Institute of Statistics, University of Neuchâtel :
                                                                         
                            Indicate if you have knowledge of "R"
                            Personnal computer is required   
 
Payment :         Postal transfer
                            Owner  : Université de Neuchâtel, Service des fonds de tiers, 2000 Neuchâtel
                            (with mention U.00413, Small area estimation course)
                            Postal account _CCP : 20-4130-2
                            IBAN : CH11 0900 0000 2000 4130 2

 

SMALL AREA ESTIMATION WITH EXAMPLES IN R

 

Time
Thursday
Friday
9:00 - 10:30
Introduction to small area estimation:
-          Design inference versus model inference.
-          Traditional direct estimators.
Basic area level model:
-          Fay-Herriot model
-          Fitting methods
-          MSE estimation
-          Extensions
10:30 - 11:00
Coffee-Break
Coffee-Break
11:00 - 12:30
Traditional indirect estimators:
-          Post-stratified synthetic estimators
-          Composite estimators
 
Basic unit level model:
-          Nested error linear regression model
-          Fitting methods
-          MSE estimation
-          Extensions
12:30 - 14:30
Lunch-Break
Lunch-Break
14:30 - 15:15
Practice 1a: Starting with R
-          Use of menus and help
-          Basic operations and R functions
-          Types of R objects
-          Creation and manipulation of objects
Practice 3a: Basic area level model: application with Spanish data on Living Conditions.
-          Fay-Herriot model
-          MSE estimation
15:15 - 15:30
Coffee-Break
Coffee-Break
15:30 - 16:15
Practice 1b. Starting with R
-          Data generation
-          Basic statistical summaries
-          Basic plotting functions
-          Manipulating data files
Practice 3b. Basic unit level model: application with Spanish data on Living Conditions.
-          Nested error linear regression model
-          MSE estimation
16:15 - 16:30
Coffee-Break
Coffee-Break
16:30 - 18:00
Practice 2. Traditional small area estimators: application with Spanish data on Living Conditions.
-          Direct estimators
-          Post-stratified synthetic estimators
-          Composite estimators
 
 
 
 
Discussion
Estimation of general non-linear parameters:
-          EB method for poverty estimation
-          Parametric bootstrap MSE estimation
 
Practice 3c. Estimation of general non-linear parameters:
application with Spanish data on Living Conditions.
 
Discussion



 

Total: 11.5 hours